How to Use the Hugging Face MCP in Windsurf

Q: How does Windsurf use the Hugging Face integration to find a specific model?

You give Windsurf a prompt, and its Cascade agent uses the listmodels tool with your criteria. It can then use getmodel or getmodeltags to refine the results and give you the best match.

Q: Can my Windsurf agent check Hugging Face dataset files before I decide to use them?

Yes. Your agent can run the listdatasetfiles tool to get a full list of files inside a dataset repository. This tells you the format and structure of the data before you download anything.

Q: What's the best way to track Hugging Face models with Windsurf?

Have your agent use the getcollection tool to retrieve a list of models you've curated. From there, it can perform other actions, like checking for new discussions on each model with listmodeldiscussions.

Let your Windsurf agent find models, inspect repos, and explore datasets on Hugging Face without you lifting a finger.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hugging Face MCP to Windsurf

Create your Vinkius account to connect Hugging Face to Windsurf and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Hugging Face with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find the Right Model, Autonomously

Stop manually searching the Hub. Give your Windsurf agent a goal, like "find a good PyTorch model for text generation," and its Cascade feature gets to work. It chains together tools to deliver exactly what you need. First, it runs `list_models` with your search terms. Then, it calls `get_model_tags` on the top results to check for the `pytorch` and `text-generation` tags. You just get the answer, not a list of links to sort through.

Inspect Repos Before You Commit

Don't download a 10GB model just to find out it's in the wrong format. Ask Windsurf, "does 'google-bert/bert-base-uncased' have safetensors files?" and let it figure it out. It's faster and saves you a ton of bandwidth. Your agent uses `list_model_files` to get a file manifest from the repository. It can check for specific filenames, look at file sizes, or even verify the contents of a subdirectory. This way, you know exactly what you're getting before you pull anything down.

This MCP Server Taps Into the Hub's Community

You can task your agent to keep an eye on community feedback for you. For instance, "summarize recent bug reports for the new Mistral model." It handles the grunt work, so you don't have to. Cascade will use `list_model_discussions` to pull recent posts, filter them for unresolved issues, and give you a summary. It can even use `create_discussion` to post a question on your behalf if you tell it to. It's like having a research assistant who lives on the Hugging Face Hub.

Setup guide

Set up Hugging Face MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Hugging Face MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Hugging Face payment history." If connected, Cascade will call the Hugging Face tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "hugging-face-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Hugging Face. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Hugging Face now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Hugging Face MCP in Windsurf

You give Windsurf a prompt, and its Cascade agent uses the `list_models` tool with your criteria. It can then use `get_model` or `get_model_tags` to refine the results and give you the best match.

Yes. Your agent can run the `list_dataset_files` tool to get a full list of files inside a dataset repository. This tells you the format and structure of the data before you download anything.

Have your agent use the `get_collection` tool to retrieve a list of models you've curated. From there, it can perform other actions, like checking for new discussions on each model with `list_model_discussions`.

Absolutely. Just tell your agent what to post and where. It will use the `create_discussion` tool to open a new topic on the specified model, dataset, or Space repository.

The server only processes the data needed for a specific tool. This includes model IDs, search terms, and discussion content you provide. All operations happen in an ephemeral, zero-trust sandbox, and your Vinkius token is the only credential needed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript